Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/howells/arc/improvenpx skills add howells/arc --skill improvegit clone --depth 1 https://github.com/howells/arcWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00085 | $0.03744 |
| Opus 5 | $0.00043 | $0.01872 |
| Sonnet 5 | $0.00017 | $0.00749 |
| Haiku 4.5 | $0.00009 | $0.00374 |
Grade A, and why
improve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 302 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<tool_restrictions>
EnterPlanMode and ExitPlanMode are banned. This skill is Arc's own structured process.
</tool_restrictions>
<arc_runtime>
Requires the full Arc bundle. Arc-owned paths (agents/, references/, disciplines/, templates/, scripts/, rules/, skills/) resolve from the plugin root — the directory containing agents/ and skills/. Everything else is the user's repository.
</arc_runtime>
<platform_context>
Adapt to the current harness rather than assuming Claude tool names — structured questions and
subagent delegation each degrade gracefully when absent. Load references/platform-tools.md
when a mapping isn't obvious.
</platform_context>
<required_reading> Read these reference files NOW:
references/finding-vetting.md— the vet pass, failure classes, and leverage rubricreferences/plan-lifecycle.md— the index schema, write discipline, and drift procedurereferences/subagent-safety.md— rules pasted into every file-less agent dispatchreferences/arc-paths.md— canonical artifact locations
Load when relevant:
references/model-strategy.md— when choosing scan-agent models </required_reading>
Improve
Turn findings into a vetted, prioritized backlog of executable plans — and keep it alive.
- Structural or interface design work (deepening modules, extracting packages, breaking up
god files) → recommend
/arc:refactor, which owns competing interface options and RFCs. - A comprehensive scored health check → recommend
/arc:audit. Improve consumes audit reports; it does not replicate audit's reviewer machinery. - Executing a plan →
/arc:implement. Improve stops when plans and index rows exist. - Shaping a feature idea →
/arc:ideate. Selected direction findings hand off there. - Do not create external tracker issues unless the user explicitly asks.
Status vocabulary note: index statuses (TODO, IN PROGRESS, DONE, BLOCKED, REJECTED)
are plan-level. They are not the per-task build-agent statuses in
references/subagent-statuses.md — DONE and BLOCKED mean different things at each level;
the rollup between them is defined in that reference.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 302 lines · 85 tokens per session scan A 57b889bd2191
improve is a skill published in the GitHub repository howells/arc (25 stars, last pushed 18d ago), licensed MIT. It adds 85 tokens to every session and 3,744 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gsd
Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents.
nw-buddy-project-reading
How the nWave buddy agent reads a project to answer questions — detection, order of inspection, and citation discipline.
triage-security-advisories
Triage the GitHub privately-reported vulnerability backlog for Activepieces — pull repository security advisories from the Security tab, scope-check against SECURITY.md, deeply validate each, compute SLA status, and propose fix plans for review. Use when the user asks to triage security advisories, work the…
debug-failed-run
Debug a failed Activepieces flow run end-to-end: given a flow run id (or BullMQ job id), find why it failed, cross-referencing the live BullMQ job + Postgres rows (SSH script on the DevOps box), the centralized ClickHouse logs (ClickStack MCP), and the code in this repo, then categorize the failed-job backlog on…
run-feedback
Use when a run of a workflow, skill, command, or test produced errors or friction worth keeping, or when executing the end-of-run Retro Global Protocol — collect findings into the feedback inbox, triage them (defect / work-item / noise), and file defects into the known-issues ledger or work-items into the backlog. NOT…
known-issues-format
Use when creating, formatting, or adding an entry to a project's thin-index ledger — docs/KNOWNISSUES.md + docs/issues/ for defects, or docs/BACKLOG.md + docs/backlog/ for work-items — or seeding either in a new project: shared index-over-records mechanics, per-registry frontmatter schema, prefix→category table…